Banned for running OpenAI models in Claude Code? Anthropic Clarifies It Was an Error
ChrisGPT · x · 2026-08-09
Recently, a user was suspended by Anthropic after following a setup to run OpenAI models through the Claude Code harness, sparking concerns that Anthropic was penalizing users for mixing competing models.
Boris Cherny, the creator of Claude Code, stepped in to clarify that this is not Anthropic's policy. He stated that a completely separate account classifier almost certainly triggered the suspension and that the team is investigating. Tibo responded by emphasizing that 'freedom of harness is important' and users should decide which model works best. Boris jokingly tried to recruit him to Anthropic, but Tibo declined, teasing that he is 'way too excited about the next couple of weeks of releases.'
More from coding & agent
- Opus 5.5 + Three.js demo stuns with water physics, fish and blossoms — nikola_mr64990 · 2026-10-16
- Grok-built linear regression bot claims $508K PnL in 125 days on Polymarket — Roger_M_Taylor · 2026-10-16
- Karpathy's knowledge engine workflow: Claude Code turns raw notes into a self-updating wiki — nikola_mr64990 · 2026-10-16
- Sierra and Meta unveil Personal Agent Protocol with Zapier as launch partner — sujingshen · 2026-10-16
- ArcKit adds 102 AI-narrated short films for commands across 14 community overlays — mcraddock · 2026-10-16
- Personal agents live or die on chaining tasks, not single-task ability — sujingshen · 2026-10-16